Coder Social home page Coder Social logo

yang-heu / paddleseg Goto Github PK

View Code? Open in Web Editor NEW

This project forked from paddlepaddle/paddleseg

0.0 0.0 0.0 338.57 MB

Easy-to-use segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks from research to industrial applications.

Home Page: https://arxiv.org/abs/2101.06175

License: Apache License 2.0

Python 93.56% CMake 0.48% C++ 0.93% Shell 1.36% Java 2.40% HTML 0.05% TypeScript 0.06% JavaScript 0.05% Cython 0.59% C 0.54%

paddleseg's Introduction

简体中文 | English

PaddleSeg

Build Status License Version python version support os

近期活动

PaddleSeg团队将举办主题为《产业图像分割应用与实战》的两日课向大家分析在交互式智能标注工具精细化分割Matting方向的研究工作。

PaddleSeg发布2.3版本,欢迎体验

  • PaddleSeg团队发表交互式分割论文EdgeFlow,升级了交互式分割工具EISeg
  • 开源两种Matting算法,经典方法DIM,和实时性方法MODNet,实现精细化人像分割。
  • 发布图像分割高阶功能,模型蒸馏模型量化方案,进一步提升模型的部署效率。

PaddleSeg介绍

PaddleSeg是基于飞桨PaddlePaddle开发的端到端图像分割开发套件,涵盖了高精度轻量级等不同方向的大量高质量分割模型。通过模块化的设计,提供了配置化驱动API调用两种应用方式,帮助开发者更便捷地完成从训练到部署的全流程图像分割应用。

  • PaddleSeg提供了语义分割、交互式分割、全景分割、Matting四大图像分割能力。


  • PaddleSeg被广泛地应用在自动驾驶、医疗、质检、巡检、娱乐等场景。


特性

  • 高精度模型:基于百度自研的半监督标签知识蒸馏方案(SSLD)训练得到高精度骨干网络,结合前沿的分割技术,提供了50+的高质量预训练模型,效果优于其他开源实现。

  • 模块化设计:支持20+主流 分割网络 ,结合模块化设计的 数据增强策略骨干网络损失函数 等不同组件,开发者可以基于实际应用场景出发,组装多样化的训练配置,满足不同性能和精度的要求。

  • 高性能:支持多进程异步I/O、多卡并行训练、评估等加速策略,结合飞桨核心框架的显存优化功能,可大幅度减少分割模型的训练开销,让开发者更低成本、更高效地完成图像分割训练。


技术交流

  • 如果你发现任何PaddleSeg存在的问题或者是建议, 欢迎通过GitHub Issues给我们提issues。
  • 欢迎加入PaddleSegQQ群

模型库总览

更多信息参见Model Zoo Overview

使用教程

实践案例

代码贡献

  • 非常感谢jm12138贡献U2-Net模型。
  • 非常感谢zjhellofss(傅莘莘)贡献Attention U-Net模型,和Dice loss损失函数。
  • 非常感谢liuguoyu666贡献U-Net++模型。
  • 非常感谢yazheng0307 (刘正)贡献快速开始教程文档。
  • 非常感谢CuberrChen贡献STDC (rethink BiSeNet) PointRend,和 Detail Aggregate损失函数。

学术引用

如果我们的项目在学术上帮助到你,请考虑以下引用:

@misc{liu2021paddleseg,
      title={PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation},
      author={Yi Liu and Lutao Chu and Guowei Chen and Zewu Wu and Zeyu Chen and Baohua Lai and Yuying Hao},
      year={2021},
      eprint={2101.06175},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{paddleseg2019,
    title={PaddleSeg, End-to-end image segmentation kit based on PaddlePaddle},
    author={PaddlePaddle Authors},
    howpublished = {\url{https://github.com/PaddlePaddle/PaddleSeg}},
    year={2019}
}

paddleseg's People

Contributors

wuyefeilin avatar michaelowenliu avatar nepeplwu avatar lutaochu avatar zeyuchen avatar sjtubinlong avatar juncaipeng avatar lielinjiang avatar joey12300 avatar haoyuying avatar geoyee avatar kazusaw1999 avatar tianlanshidai avatar furao123 avatar pennypm avatar yzl19940819 avatar shiyutang avatar channingss avatar parap1uie-s avatar chliang avatar mrxlt avatar yazheng0307 avatar qingshuchen avatar jm12138 avatar linhandev avatar lingorx avatar beyondyourself avatar taixiurong avatar txyugood avatar cuberrchen avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.